scholarly journals Towards Reinforcement based Learning of an Assembly Process for Human Robot Collaboration

2019 ◽  
Vol 38 ◽  
pp. 1491-1498
Author(s):  
Sharath Chandra Akkaladevi ◽  
Matthias Plasch ◽  
Andreas Pichler ◽  
Markus Ikeda
Keyword(s):  
Assembly Process ◽  
Human Robot Collaboration

3D long-term recurrent convolutional networks for human sub-assembly recognition in human-robot collaboration

2020 ◽  
Vol 40 (4) ◽  
pp. 655-662 ◽  
Author(s):  
Xianhe Wen ◽  
Heping Chen
Keyword(s):  
High Precision ◽  
Short Term Memory ◽  
Recognition Accuracy ◽  
Model Parameters ◽  
Assembly Process ◽  
Content Type ◽  
Convolutional Networks ◽  
3D Cnn ◽  
Human Robot Collaboration

Purpose Human assembly process recognition in human–robot collaboration (HRC) has been studied recently. However, most research works do not cover high-precision and long-timespan sub-assembly recognition. Hence this paper aims to deal with this problem. Design/methodology/approach To deal with the above-mentioned problem, the authors propose a 3D long-term recurrent convolutional networks (LRCN) by combining 3D convolutional neural networks (CNN) with long short-term memory (LSTM). 3D CNN behaves well in human action recognition. But when it comes to human sub-assembly recognition, the accuracy of 3D CNN is very low and the number of model parameters is huge, which limits its application in human sub-assembly recognition. Meanwhile, LSTM has the incomparable superiority of long-time memory and time dimensionality compression ability. Hence, by combining 3D CNN with LSTM, the new approach can greatly improve the recognition accuracy and reduce the number of model parameters. Findings Experiments were performed to validate the proposed method and preferable results have been obtained, where the recognition accuracy increases from 82% to 99%, recall ratio increases from 95% to 100% and the number of model parameters is reduced more than 8 times. Originality/value The authors focus on a new problem of high-precision and long-timespan sub-assembly recognition in the area of human assembly process recognition. Then, the 3D LRCN method is a new method with high-precision and long-timespan recognition ability for human sub-assembly recognition compared to 3D CNN method. It is extraordinarily valuable for the robot in HRC. It can help the robot understand what the sub-assembly human cooperator has done in HRC.

scholarly journals POWER AND FORCE LIMITING TECHNIQUE AT COLLABORATIVE WORKPLACE

2021 ◽  
Vol 2021 (2) ◽  
pp. 4424-4427
Author(s):  
IVAN VIRGALA ◽  
◽  
ERIK PRADA ◽  
MAREK VAGAS ◽  
◽  
...  
Keyword(s):  
Human Body ◽  
Automotive Industry ◽  
Robotic System ◽  
Assembly Process ◽  
Automated Assembly ◽  
Short Overview ◽  
Specific Contact ◽  
Human Robot Collaboration ◽  
Dual Arm ◽  
Skilled Staff

Nowadays, the automotive industry still incorporates collaborative robots and their applications into the less traditional processes to automate them. The purpose is to make up for the skill gap, retain skilled staff, attract the younger generation, and increase quality. The paper brings a short overview of the automated collaborative workplace, including the PFL technique description and possibilities. Also, human-robot collaboration (HRC) is elaborated together with the example of such an automated workplace (with dual-arm robotic system participation). The specific contact (transient, quasi-static) between the human body and robotic system is described to fulfill the HRC and PFL technique. It also summarizes and explains ISO / TS 15066 details to apply this technique at automated assembly process example.

Adaptive Mensch-Roboter-Kollaboration in der Montage*/Adaptive human-robot collaboration in assembly – Manual Processes in the Internet of Production – Uncertainty in a digitally simulated world?

2019 ◽  
Vol 109 (09) ◽  
pp. 694-698
Author(s):  
H. Petruck ◽  
A. Mertens ◽  
V. Nitsch
Keyword(s):  
Interaction Design ◽  
Time Measurement ◽  
Human Robot Interaction ◽  
The Internet ◽  
Assembly Process ◽  
Robot Interaction ◽  
Manual Assembly ◽  
Time Prediction ◽  
Human Robot Collaboration ◽  
Faktor Mensch

Dieser Beitrag beschreibt eine Möglichkeit, den Faktor Mensch bei der Planung manueller Montagevorgänge in der Mensch-Roboter-Kollaboration (MRK) zu berücksichtigen. Das Ziel ist die echtzeitfähige Prädiktion der Dauer des Montageprozesses auf Mikro-, Meso- und Makro-Ebene der Produktion auf Basis von Methods-Time Measurement (MTM). Darauf aufbauend soll durch Adaption der Montagedauer eine ergonomische Interaktion zwischen Mensch und Roboter geschaffen werden.   This paper describes one way to consider human factors when planning manual assembly processes in human-robot collaboration (HRC). The goal is the real-time prediction of the duration of the assembly process on the micro-, meso- and macro-level of the production based on Methods-Time Measurement (MTM). This prediction is then used for an ergonomic human-robot interaction design by adapting the predicted assembly durations.

Pathway Complexity in the Stacking of Imine-linked Macrocycles Related to Two-Dimensional Covalent Organic Frameworks

2019 ◽  
Author(s):  
Shiwei Wang ◽  
Anton Chavez ◽  
Simil Thomas ◽  
Hong Li ◽  
Nathan C. Flanders ◽  
...  
Keyword(s):  
Temperature Dependence ◽  
Structural Similarity ◽  
Discrete Models ◽  
Side Chains ◽  
Two Dimensional ◽  
Assembly Process ◽  
Covalent Organic Frameworks ◽  
Electron Systems ◽  
Monomer Structure ◽  
Kinetic Traps

This work reports on the assembly of imine-linked macrocycles that serve as models of two-dimensional covalent organic frameworks (2D COFs). Interlayer interactions play an important role in the formation of 2D COFs, yet the effect of monomer structure on COF formation, crystallinity, and susceptibility to exfoliation are not well understood. For example, monomers with both electron-rich and electron-poor π-electron systems have been proposed to strengthen interlayer inter-actions and improve crystallinity. Here we probe these effects by studying the stacking behavior of imine-linked macrocycles that represent discrete models of 2D COFs. <div><br></div><div>Specifically, macrocycles based on terephthaldehyde (PDA) or 2,5-dimethoxyterephthaldehyde (DMPDA) stack upon cooling molecularly dissolved solutions. Both macrocycles assemble cooperatively with similar ΔHe values of -97 kJ/mol and -101 kJ/mol, respectively, although the DMPDA macrocycle assembly process showed a more straightforward temperature dependence. Circular dichroism spectroscopy performed on macrocycles bearing chiral side chains revealed a helix reversion process for the PDA macrocycles that was not observed for the DMPDA macrocycles. <br></div><div><br></div><div>Given the structural similarity of these monomers, these findings demonstrate that the stacking processes associated with nanotubes derived from these macrocycles, as well as for the corresponding COFs, are complex and susceptible to kinetic traps, casting doubt on the relevance of thermodynamic arguments for improving materials quality. <br></div>

Intermittent Failures in High Pin Count Packaging

2006 ◽  
Author(s):  
Ramesh Varma ◽  
Richard Brooks ◽  
Ronald Twist ◽  
James Arnold ◽  
Cleston Messick
Keyword(s):  
Failure Analysis ◽  
Shape Analysis ◽  
State Of The Art ◽  
Process Variation ◽  
High Reliability ◽  
Temperature Cycling ◽  
Assembly Process ◽  
System Failures ◽  
Industrial Grade ◽  
Corrective Actions

Abstract In a prequalification effort to evaluate the assembly process for the industrial grade high pin count devices for use in a high reliability application, one device exhibited characteristics that, without corrective actions and/or extensive screening, may lead to intermittent system failures and unacceptable reliability. Five methodologies confirmed this conclusion: (1) low post-decapsulation wire pull results; (2) bond shape analysis showed process variation; (3) Failure Analysis (FA) using state of the art equipment determined the root causes and verified the low wire pull results; (4) temperature cycling parts while monitoring, showed intermittent failures, and (5) parts tested from other vendors using the same techniques passed all limits.

Preparation of BSA Nanoparticles by Desolvation Technique Using Acetone as Desolvating Agent

2012 ◽  
Vol 5 (1) ◽  
pp. 1643-1647
Author(s):  
Krishna Sailaja A ◽  
Amareshwar P
Keyword(s):  
Aqueous Solution ◽  
Standard Deviation ◽  
Process Parameters ◽  
Self Assembly ◽  
Size Control ◽  
Polymeric Materials ◽  
Preparation Condition ◽  
Assembly Process ◽  
Average Size

In order to see the functionality and toxicity of nanoparticles in various food and drug applications, it is important to establish procedures to prepare nanoparticles of a controlled size. Desolvation is a thermodynamically driven self-assembly process for polymeric materials. In this study, we prepared BSA nanoparticles using the desolvation technique using acetone as desolvating agent. Acetone was added intermittently into 1% BSA solution at different pH under stirring at 700 rpm. Amount of acetone added, intermittent timeline of acetone addition, and pH of solution were considered as process parameters to be optimized. The effect of the process parameters on size of the nanoparticles was studied. The results indicated that the size control of BSA nanoparticles was achieved by adding acetone intermittently. The standard deviation of average size of BSA nanoparticles at each preparation condition was minimized by adding acetone intermittently. The intermittent addition in polymeric aqueous solution can be useful for size control for food or drug applications.  

Sign in / Sign up

Export Citation Format

Share Document